# City-GAN: Learning architectural styles using a custom Conditional GAN architecture

arXiv: https://arxiv.org/abs/1907.05280 · HTML: https://mlsanity.com/paper/1907.05280/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2019.

## Built on by (most cited first, 5 of 5)

- [Automated Urban Planning for Reimagining City Configuration via Adversarial Learning: Quantification, Generation, and Evaluation](https://mlsanity.com/paper/2112.14699/) (2021)
- [FaccAID: A Transformer Model for Neuro-Symbolic Facade Reconstruction](https://mlsanity.com/paper/2406.01829/) (2024)
- [Re-designing cities with conditional adversarial networks](https://mlsanity.com/paper/2104.04013/) (2021)
- [Generating floorplans for various building functionalities via latent diffusion model](https://mlsanity.com/paper/2412.06859/) (2024)
- [Virtual Urbanism: An AI-Driven Framework for Quantifying Urban Identity. A Tokyo-Based Pilot Study Using Diffusion-Generated Synthetic Environments](https://mlsanity.com/paper/2601.13846/) (2026)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) are a well-known technique that is trained on samples (e.g. pictures of fruits) and which after training is able to generate realistic new samples. Conditional GANs (CGANs) additionally provide label information for subclasses (e.g. apple, orange, pear) which enables the GAN to learn more easily and increase the quality of its output samples. We use GANs to learn architectural features of major cities and to generate images of buildings which do not exist. We show that currently available GAN and CGAN architectures are unsuited for this task and propose a custom architecture and demonstrate that our architecture has superior performance for this task and verify its capabilities with extensive experiments.